4 papers
Human-in-the-Loop Distributed Control of Grid-Interactive Buildings for Demand Response Participation
Kasra Mazarei Saadabadi, Dongming Wang, Wei Ren +2
This paper proposes a human-in-the-loop distributed consensus control approach for demand-side management across multiple buildings. Specifically, a novel framework is introduced i…
Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces
Dongming Wang, Pengcheng Dai, Wenwu Yu +1
We develop the Continuous Distributed Coupled Policy Gradient (CDCPG) algorithm for cooperative reinforcement learning in networked Markov decision processes with continuous state…
Distributed Stochastic Zeroth-Order Optimization with Compressed Communication
Youqing Hua, Shuai Liu, Yiguang Hong +1
The dual challenges of prohibitive communication overhead and the impracticality of gradient computation due to data privacy or black-box constraints in distributed systems motivat…
Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning
Pengcheng Dai, Yuanqiu Mo, Wenwu Yu +1
This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative…